metapath2vec

TLDR

Heterogeneous networks contain multiple node and link types, which render conventional embedding techniques infeasible. The study develops scalable representation learning models for heterogeneous networks. Metapath2vec employs meta‑path‑based random walks and a heterogeneous skip‑gram to embed nodes, while metapath2vec++ additionally models structural and semantic correlations simultaneously. Extensive experiments show that metapath2vec and metapath2vec++ outperform state‑of‑the‑art embedding models in node classification, clustering, and similarity search, and discern structural and semantic correlations between diverse network objects.

Abstract

We study the problem of representation learning in heterogeneous networks. Its unique challenges come from the existence of multiple types of nodes and links, which limit the feasibility of the conventional network embedding techniques. We develop two scalable representation learning models, namely metapath2vec and metapath2vec++. The metapath2vec model formalizes meta-path-based random walks to construct the heterogeneous neighborhood of a node and then leverages a heterogeneous skip-gram model to perform node embeddings. The metapath2vec++ model further enables the simultaneous modeling of structural and semantic correlations in heterogeneous networks. Extensive experiments show that metapath2vec and metapath2vec++ are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, such as node classification, clustering, and similarity search, but also discern the structural and semantic correlations between diverse network objects.